大作业

import os
import numpy as np
import sys
from datetime import datetime
import gc
path = 'F:\\jj147'


# 导入结巴库，并将需要用到的词库加进字典
import jieba
# 导入停用词：
with open(r'F:\stopsCN.txt', encoding='utf-8') as f:
    stopwords = f.read().split('\n')

def processing(tokens):
    # 去掉非字母汉字的字符
    tokens = "".join([char for char in tokens if char.isalpha()])
    # 结巴分词
    tokens = [token for token in jieba.cut(tokens,cut_all=True) if len(token) >=2]
    # 去掉停用词
    tokens = " ".join([token for token in tokens if token not in stopwords])
    return tokens

tokenList = []
targetList = []
# 用os.walk获取需要的变量，并拼接文件路径再打开每一个文件
for root,dirs,files in os.walk(path):
    for f in files:
        filePath = os.path.join(root,f)
        with open(filePath, encoding='utf-8') as f:
            content = f.read()
            # 获取新闻类别标签，并处理该新闻
        target = filePath.split('\\')[-2]
        targetList.append(target)
        tokenList.append(processing(content))


#划分训练集和测试，用TF-IDF算法进行单词权值的计算
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
vectorizer= TfidfVectorizer()
x_train,x_test,y_train,y_test=train_test_split(tokenList,targetList,test_size=0.2)
X_train=vectorizer.fit_transform(x_train)
X_test=vectorizer.transform(x_test)


#构建贝叶斯模型
from sklearn.naive_bayes import MultinomialNB #用于离散特征分类，文本分类单词统计，以出现的次数作为特征值
mulp=MultinomialNB ()
mulp_NB=mulp.fit(X_train,y_train)
#对模型进行预测
y_predict=mulp.predict(X_test)
# # 从sklearn.metrics里导入classification_report做分类的性能报告
from sklearn.metrics import classification_report
print('模型的准确率为：', mulp.score(X_test, y_test))
print('classification_report:\n',classification_report(y_test, y_predict))

# 将预测结果和实际结果进行对比
import collections
import matplotlib.pyplot as plt

# 统计测试集和预测集的各类新闻个数
testCount = collections.Counter(y_test)
predCount = collections.Counter(y_predict)
print('实际：',testCount,'\n', '预测', predCount)

# 建立标签列表，实际结果列表，预测结果列表，
nameList = list(testCount.keys())
testList = list(testCount.values())
predictList = list(predCount.values())
x = list(range(len(nameList)))
print("新闻类别：",nameList,'\n',"实际：",testList,'\n',"预测：",predictList)